org.deeplearning4j.nn.layers

Class BaseLayer

java.lang.Object

org.deeplearning4j.nn.layers.BaseLayer

All Implemented Interfaces:

Serializable, Cloneable, Layer

Direct Known Subclasses:

ConvolutionDownSampleLayer, Layer, OutputLayer, SubsamplingLayer

public abstract class BaseLayer
extends Object
implements Layer

A layer with a bias and activation function

Author:

Adam Gibson

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
protected org.nd4j.linalg.api.ndarray.INDArray	b
protected NeuralNetConfiguration	conf
protected org.nd4j.linalg.api.ndarray.INDArray	dropoutMask
protected org.nd4j.linalg.api.ndarray.INDArray	input
protected org.nd4j.linalg.api.ndarray.INDArray	W

Constructor Summary

Constructors

Constructor and Description
BaseLayer(NeuralNetConfiguration conf, org.nd4j.linalg.api.ndarray.INDArray W, org.nd4j.linalg.api.ndarray.INDArray b, org.nd4j.linalg.api.ndarray.INDArray input)

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	activate() Trigger an activation with the last specified input
org.nd4j.linalg.api.ndarray.INDArray	activate(org.nd4j.linalg.api.ndarray.INDArray input) Initialize the layer with the given input and return the activation for this layer given this input
protected void	applyDropOutIfNecessary(org.nd4j.linalg.api.ndarray.INDArray input)
Layer	clone()
NeuralNetConfiguration	conf()
protected org.nd4j.linalg.api.ndarray.INDArray	createBias()
protected org.nd4j.linalg.api.ndarray.INDArray	createWeightMatrix()
org.nd4j.linalg.api.ndarray.INDArray	getB()
org.nd4j.linalg.api.ndarray.INDArray	getInput()
org.nd4j.linalg.api.ndarray.INDArray	getW()
void	merge(Layer l, int batchSize) Averages the given logistic regression from a mini batch in to this one
org.nd4j.linalg.api.ndarray.INDArray	preOutput(org.nd4j.linalg.api.ndarray.INDArray x) Classify input
void	setB(org.nd4j.linalg.api.ndarray.INDArray b)
void	setConfiguration(NeuralNetConfiguration conf)
void	setInput(org.nd4j.linalg.api.ndarray.INDArray input)
void	setW(org.nd4j.linalg.api.ndarray.INDArray W)
String	toString()
Layer	transpose() Return a transposed copy of the weights/bias (this means reverse the number of inputs and outputs on the weights)

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

W

protected org.nd4j.linalg.api.ndarray.INDArray W

b

protected org.nd4j.linalg.api.ndarray.INDArray b

input

protected org.nd4j.linalg.api.ndarray.INDArray input

conf

protected NeuralNetConfiguration conf

dropoutMask

protected org.nd4j.linalg.api.ndarray.INDArray dropoutMask

Constructor Detail

BaseLayer

public BaseLayer(NeuralNetConfiguration conf,
                 org.nd4j.linalg.api.ndarray.INDArray W,
                 org.nd4j.linalg.api.ndarray.INDArray b,
                 org.nd4j.linalg.api.ndarray.INDArray input)

Method Detail

createBias

protected org.nd4j.linalg.api.ndarray.INDArray createBias()

createWeightMatrix

protected org.nd4j.linalg.api.ndarray.INDArray createWeightMatrix()

preOutput

public org.nd4j.linalg.api.ndarray.INDArray preOutput(org.nd4j.linalg.api.ndarray.INDArray x)

Classify input

Specified by:

preOutput in interface Layer

Parameters:

x - the input (can either be a matrix or vector) If it's a matrix, each row is considered an example and associated rows are classified accordingly. Each row will be the likelihood of a label given that example

Returns:

a probability distribution for each row

activate

public org.nd4j.linalg.api.ndarray.INDArray activate()

Description copied from interface: Layer

Trigger an activation with the last specified input

Specified by:

activate in interface Layer

Returns:

the activation of the last specified input

activate

public org.nd4j.linalg.api.ndarray.INDArray activate(org.nd4j.linalg.api.ndarray.INDArray input)

Description copied from interface: Layer

Initialize the layer with the given input and return the activation for this layer given this input

Specified by:

activate in interface Layer

Parameters:

input - the input to use

Returns:

conf

public NeuralNetConfiguration conf()

Specified by:

conf in interface Layer

setConfiguration

public void setConfiguration(NeuralNetConfiguration conf)

Specified by:

setConfiguration in interface Layer

getW

public org.nd4j.linalg.api.ndarray.INDArray getW()

Specified by:

getW in interface Layer

setW

public void setW(org.nd4j.linalg.api.ndarray.INDArray W)

Specified by:

setW in interface Layer

getB

public org.nd4j.linalg.api.ndarray.INDArray getB()

Specified by:

getB in interface Layer

setB

public void setB(org.nd4j.linalg.api.ndarray.INDArray b)

Specified by:

setB in interface Layer

getInput

public org.nd4j.linalg.api.ndarray.INDArray getInput()

Specified by:

getInput in interface Layer

setInput

public void setInput(org.nd4j.linalg.api.ndarray.INDArray input)

Specified by:

setInput in interface Layer

applyDropOutIfNecessary

protected void applyDropOutIfNecessary(org.nd4j.linalg.api.ndarray.INDArray input)

merge

public void merge(Layer l,
                  int batchSize)

Averages the given logistic regression from a mini batch in to this one

Parameters:

l - the logistic regression to average in to this one

batchSize - the batch size

clone

public Layer clone()

Specified by:

clone in interface Layer

Overrides:

clone in class Object

transpose

public Layer transpose()

Description copied from interface: Layer

Return a transposed copy of the weights/bias (this means reverse the number of inputs and outputs on the weights)

Specified by:

transpose in interface Layer

Returns:

the transposed layer

toString

public String toString()

Overrides:

toString in class Object